Elamur Research⌕
☰
home / authors / Zhekai Zhang

Zhekai Zhang

Zhekai Zhang has 3 papers in our library, in 2019–2024, most of them on Efficient models & compression, Language models & pretraining; often with Song Han, Chuang Gan, Guangxuan Xiao.

3 papers in our library · 2019–2024

OpenAlex · ORCID · h-index 12 · 58 works · 1,159 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 392 times in our library · ⭐ Paper Stars ranking: #2897

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢NvidiaSanta Clara · United States2026 · 1 papercurrent🎓Massachusetts Institute of TechnologyCambridge · United States2019–2025 · 12 papers🎓Audencia Business SchoolNantes · France2025Employment since 2025 · Assistant Professor🎓Shenzhen UniversityShenzhen · China2025Employment since 2025 · Assistant Professor, Shenzhen Audencia Financial Technology Institute

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksComputer Vision and Pattern Recognition · 3 worksArtificial Intelligence · 2 worksArts and Humanities · 1 workHardware and Architecture · 2 worksLanguage and Linguistics · 1 workEngineering · 1 workElectrical and Electronic Engineering · 1 work

🧭 Topics 2Research subjects and languages the work is about.Efficient models & compression · 2 worksLanguage models & pretraining · 1 work

 Works by year

2020s

20241 paper20201 paper

2010s

20191 paper

 Papers

The most cited first (OpenAlex and our library).

  1. SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning (2020 · 534 citations)
    Attention-based NLP models such as BERT and GPT-2 run slowly on CPUs and GPUs. The cost grows quadratically with input length, much of the time goes to moving data rather than arithmetic, and existing accelerators were built for CNNs and RNNs. SpAtten (HPCA 2021) is an algorithm-hardware co-design that cuts both…
  2. Once-for-All: Train One Network and Specialize it for Efficient Deployment (2019 · 252 citations)
    Deploying neural networks across many devices (phones, CPUs, GPUs, FPGAs, microcontrollers) and latency budgets usually means designing or searching a new architecture and training it from scratch for each target, so the cost grows with every new scenario.
  3. QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving (2024 · 120 citations)
    Low-bit integer quantization promises faster LLM inference, but INT4 approaches have mostly helped small-batch edge scenarios.

 Co-authors here

7 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 392 times (of the 149,439 papers whose bibliographies we read); 27 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhekai-zhang/